{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/unsupervised-latent-tree-induction-with-deep","title":"Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Autoencoders","arxiv_id":"1904.02142","date":"2019-04-03","proceeding":null,"authors":["Andrew Drozdov","Pat Verga","Mohit Yadav","Mohit Iyyer","Andrew McCallum"],"abstract":"We introduce deep inside-outside recursive autoencoders (DIORA), a\nfully-unsupervised method for discovering syntax that simultaneously learns\nrepresentations for constituents within the induced tree. Our approach predicts\neach word in an input sentence conditioned on the rest of the sentence and uses\ninside-outside dynamic programming to consider all possible binary trees over\nthe sentence. At test time the CKY algorithm extracts the highest scoring\nparse. DIORA achieves a new state-of-the-art F1 in unsupervised binary\nconstituency parsing (unlabeled) in two benchmark datasets, WSJ and MultiNLI.","url_abs":"http://arxiv.org/abs/1904.02142v2","url_pdf":"http://arxiv.org/pdf/1904.02142v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"unsupervised-latent-tree-induction-with-deep","repo_url":"https://github.com/iesl/diora","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"unsupervised-latent-tree-induction-with-deep","repo_url":"https://github.com/i-machine-think/emergent_grammar_induction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"unsupervised-latent-tree-induction-with-deep","repo_url":"https://github.com/rgalhama/diora","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"constituency-parsing","task_name":"Constituency Parsing"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1904.02142","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.02142"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/iesl/diora","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/rgalhama/diora","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/i-machine-think/emergent_grammar_induction","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":2,"ran_draft_wrong":2,"unverified":12},"by_repo_kind":{"official":{"samples":6,"ran":4,"repositories":1},"listed":{"samples":10,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"be633fb138549fac","entry":"flatten_tree","repo":"iesl/diora","repo_kind":"official","path":"pytorch/diora/scripts/parse.py","file_url":"https://github.com/iesl/diora/blob/HEAD/pytorch/diora/scripts/parse.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"be633fb138549fac"}},{"code_sha256_prefix":"dc405b16a06bb314","entry":"get_ptb_format_from_diora_tree","repo":"iesl/diora","repo_kind":"official","path":"pytorch/diora/scripts/evalb.py","file_url":"https://github.com/iesl/diora/blob/HEAD/pytorch/diora/scripts/evalb.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dc405b16a06bb314"}},{"code_sha256_prefix":"97a72c5a047620b9","entry":"postprocess","repo":"iesl/diora","repo_kind":"official","path":"pytorch/diora/scripts/parse.py","file_url":"https://github.com/iesl/diora/blob/HEAD/pytorch/diora/scripts/parse.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"97a72c5a047620b9"}},{"code_sha256_prefix":"88ba8def413739a5","entry":"remove_using_flat_mask","repo":"iesl/diora","repo_kind":"official","path":"pytorch/diora/scripts/parse.py","file_url":"https://github.com/iesl/diora/blob/HEAD/pytorch/diora/scripts/parse.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"88ba8def413739a5"}},{"code_sha256_prefix":"1e93d604e778f7ba","entry":"calculate_freq_dist","repo":"rgalhama/diora","repo_kind":"listed","path":"pytorch/diora/blocks/negative_sampler.py","file_url":"https://github.com/rgalhama/diora/blob/HEAD/pytorch/diora/blocks/negative_sampler.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1e93d604e778f7ba"}},{"code_sha256_prefix":"2fbf0a00fadbc516","entry":"choose_negative_samples","repo":"rgalhama/diora","repo_kind":"listed","path":"pytorch/diora/blocks/negative_sampler.py","file_url":"https://github.com/rgalhama/diora/blob/HEAD/pytorch/diora/blocks/negative_sampler.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2fbf0a00fadbc516"}},{"code_sha256_prefix":"eafe1b97157e9ce2","entry":"configure_logger","repo":"rgalhama/diora","repo_kind":"listed","path":"pytorch/diora/logging/configuration.py","file_url":"https://github.com/rgalhama/diora/blob/HEAD/pytorch/diora/logging/configuration.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"eafe1b97157e9ce2"}},{"code_sha256_prefix":"da754532b4ccd8b5","entry":"get_inside_states","repo":"rgalhama/diora","repo_kind":"listed","path":"pytorch/diora/net/diora.py","file_url":"https://github.com/rgalhama/diora/blob/HEAD/pytorch/diora/net/diora.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"da754532b4ccd8b5"}},{"code_sha256_prefix":"211c02eb344ded7f","entry":"get_loss_funcs","repo":"rgalhama/diora","repo_kind":"listed","path":"pytorch/diora/net/trainer.py","file_url":"https://github.com/rgalhama/diora/blob/HEAD/pytorch/diora/net/trainer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"211c02eb344ded7f"}},{"code_sha256_prefix":"749881a9d1474de6","entry":"get_offset_cache","repo":"rgalhama/diora","repo_kind":"listed","path":"pytorch/diora/net/offset_cache.py","file_url":"https://github.com/rgalhama/diora/blob/HEAD/pytorch/diora/net/offset_cache.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"749881a9d1474de6"}},{"code_sha256_prefix":"49e41cb57b27ffc0","entry":"get_ptb_format_from_nltk_tree","repo":"iesl/diora","repo_kind":"official","path":"pytorch/diora/scripts/evalb.py","file_url":"https://github.com/iesl/diora/blob/HEAD/pytorch/diora/scripts/evalb.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"49e41cb57b27ffc0"}},{"code_sha256_prefix":"979fac5ee1a98b47","entry":"inside_compose","repo":"rgalhama/diora","repo_kind":"listed","path":"pytorch/diora/net/diora.py","file_url":"https://github.com/rgalhama/diora/blob/HEAD/pytorch/diora/net/diora.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"979fac5ee1a98b47"}},{"code_sha256_prefix":"bd841f155656f991","entry":"inside_score","repo":"rgalhama/diora","repo_kind":"listed","path":"pytorch/diora/net/diora.py","file_url":"https://github.com/rgalhama/diora/blob/HEAD/pytorch/diora/net/diora.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd841f155656f991"}},{"code_sha256_prefix":"056af46d1aab23e9","entry":"load_experiment","repo":"rgalhama/diora","repo_kind":"listed","path":"pytorch/diora/utils/checkpoint.py","file_url":"https://github.com/rgalhama/diora/blob/HEAD/pytorch/diora/utils/checkpoint.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"056af46d1aab23e9"}},{"code_sha256_prefix":"9d127c4fb21d72be","entry":"pick","repo":"rgalhama/diora","repo_kind":"listed","path":"pytorch/diora/misc/convert_conll_to_jsonl.py","file_url":"https://github.com/rgalhama/diora/blob/HEAD/pytorch/diora/misc/convert_conll_to_jsonl.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9d127c4fb21d72be"}},{"code_sha256_prefix":"2ef8eba0e3a234ce","entry":"remove_punctuation_from_tree","repo":"iesl/diora","repo_kind":"official","path":"pytorch/diora/scripts/evalb.py","file_url":"https://github.com/iesl/diora/blob/HEAD/pytorch/diora/scripts/evalb.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2ef8eba0e3a234ce"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}